{"id":"https://openalex.org/W4388187260","doi":"https://doi.org/10.1145/3581783.3612850","title":"Answer-Based Entity Extraction and Alignment for Visual Text Question Answering","display_name":"Answer-Based Entity Extraction and Alignment for Visual Text Question Answering","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388187260","doi":"https://doi.org/10.1145/3581783.3612850"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077962053","display_name":"Mohan Jing","orcid":"https://orcid.org/0009-0003-3891-9207"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Jing","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-3891-9207","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102895395","display_name":"W Liu","orcid":"https://orcid.org/0009-0005-4385-2734"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Liu","raw_affiliation_strings":["University of Science and Technology Beijing, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-4385-2734","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Hefei, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087973257","display_name":"Tongxu Luo","orcid":"https://orcid.org/0009-0000-4576-1178"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongxu Luo","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-4576-1178","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459239","display_name":"Bingyuan Zhang","orcid":"https://orcid.org/0009-0003-6000-6631"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyuan Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-6000-6631","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045007834","display_name":"Keda Lu","orcid":"https://orcid.org/0009-0006-8974-3813"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keda Lu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-8974-3813","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065062791","display_name":"Fangyu Lei","orcid":"https://orcid.org/0000-0002-1678-1118"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Lei","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1678-1118","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047888605","display_name":"Jianqing Sun","orcid":"https://orcid.org/0009-0007-3598-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Sun","raw_affiliation_strings":["Unisound AI Technology Co.,Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3598-8564","affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co.,Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039730743","display_name":"Jiaen Liang","orcid":"https://orcid.org/0009-0001-8309-1301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co.,Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8309-1301","affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co.,Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3368,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59645077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9487","last_page":"9491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8665794730186462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8050416707992554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7054325938224792},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.561779260635376},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5434936881065369},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49488991498947144},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47277262806892395},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4713703393936157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4508573114871979},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4347577393054962}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8665794730186462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050416707992554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7054325938224792},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.561779260635376},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5434936881065369},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49488991498947144},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47277262806892395},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4713703393936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4508573114871979},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4347577393054962},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612850","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2884093133","https://openalex.org/W2952372688","https://openalex.org/W2963191264","https://openalex.org/W2963954913","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2970869018","https://openalex.org/W3034500398","https://openalex.org/W3034837210","https://openalex.org/W3035497460","https://openalex.org/W3185066916","https://openalex.org/W4312080192","https://openalex.org/W4386076140"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W1984061923","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W3093385053","https://openalex.org/W4389682534","https://openalex.org/W4390091918","https://openalex.org/W3045060014","https://openalex.org/W4390241396"],"abstract_inverted_index":{"As":[0],"a":[1,14,67],"variant":[2],"of":[3,76,93,110],"visual":[4,8],"question":[5,10],"answering":[6,11],"(VQA),":[7],"text":[9,39],"(VTQA)":[12],"provides":[13],"text-image":[15],"pair":[16],"for":[17],"each":[18],"question.":[19],"Text":[20],"utilizes":[21],"named":[22,36],"entities":[23,37],"to":[24,31,52,65],"describe":[25],"corresponding":[26],"image.":[27],"Consequently,":[28],"the":[29,91,104,107,122,135],"ability":[30],"perform":[32],"multi-hop":[33,72],"reasoning":[34],"using":[35],"between":[38,98],"and":[40,61,70,84,95,100,103,129],"image":[41],"becomes":[42],"critically":[43],"important.":[44],"However,":[45],"existing":[46],"models":[47],"pay":[48],"relatively":[49],"less":[50],"attention":[51],"this":[53],"aspect.":[54],"Therefore,":[55],"we":[56],"propose":[57],"Answer-Based":[58],"Entity":[59],"Extraction":[60],"Alignment":[62],"Model":[63],"(AEEA)":[64],"enable":[66],"comprehensive":[68],"understanding":[69],"support":[71],"reasoning.":[73],"The":[74,88],"core":[75],"AEEA":[77],"lies":[78],"in":[79,115,138],"two":[80],"main":[81],"components:":[82],"AKECMR":[83],"answer":[85],"aware":[86],"predictor.":[87],"former":[89],"emphasizes":[90],"alignment":[92],"modalities":[94],"effectively":[96],"distinguishes":[97],"intra-modal":[99],"inter-modal":[101],"information,":[102],"latter":[105],"prioritizes":[106],"full":[108],"utilization":[109],"intrinsic":[111],"semantic":[112],"information":[113],"contained":[114],"answers":[116],"during":[117],"training.":[118],"Our":[119],"model":[120],"outperforms":[121],"baseline":[123],"by":[124],"2.24%":[125],"on":[126,131],"test-dev":[127],"set":[128],"1.06%":[130],"test":[132],"set,":[133],"securing":[134],"third":[136],"place":[137],"VTQA2023(English).":[139]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}